graph-connect-api

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script .claude/scripts/code_graph using Python to process project data and generate graph edges. This execution is confined to the local project environment and aligns with the tool's primary purpose.
  • [PROMPT_INJECTION]: Analysis identifies a surface for indirect prompt injection due to the ingestion of untrusted source code and configuration files.
  • Ingestion points: Processes project files including frontend components (Angular, React, Vue, Svelte, Next.js), backend controllers (.NET, Spring, Express, FastAPI, Django, Rails, Go), and docs/project-config.json.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat the analyzed code as untrusted data rather than instructions.
  • Capability inventory: The skill has access to Bash (for executing the local graph tool) and Read (for file scanning).
  • Sanitization: No sanitization or filtering logic is specified for the code content retrieved during the connection detection process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 06:11 AM